| 基于动态裁剪频繁模式树的频繁项集并发挖掘算法 |
| |
| 引用本文： | 宋威,刘文博,李晋宏.基于动态裁剪频繁模式树的频繁项集并发挖掘算法[J].山东大学学报(工学版),2011,41(4):49-55. |
| |
| 作者姓名： | 宋威 刘文博 李晋宏 |
| |
| 作者单位： | 北方工业大学信息工程学院, 北京 100144 |
| |
| 基金项目： | 国家自然科学基金资助项目(51075423); 北京市属市管高等学校人才强教计划资助项目(PHR20100509,PHR201108057); 北京市优秀人才培养资助项目(2009D005002000009) |
| |
| 摘 要： | 为解决FP(frequent pattern)-growth算法中构造频繁模式树(FP-树)所带来的存储和遍历开销较大的问题,提出了一种基于动态裁剪FP-树的频繁项集并发算法Dynamic prune。一方面,通过记录FP 树构造过程中频繁项目计数的变化,实现了FP 树的动态剪枝;另一方面,使用并发策略达到了边构造FP-树,边挖掘频繁项集的效果。与FP growth算法相比,Dynamic-prune无需先构造整棵FP-树再挖掘频繁项集,节省了FP-树的存储开销。实验结果表明Dynamic-prune在运行效率和可扩展性上均优于FP growth算法。
|
| 关 键 词： | 数据挖掘 频繁模式树 频繁项集 动态剪枝 并发 |
| 收稿时间： | 2011-04-15 |
Concurrent frequent itemsets mining algorithm based on dynamic prune of FP-tree |
| |
| SONG Wei,LIU Wen-bo,LI Jin-hong.Concurrent frequent itemsets mining algorithm based on dynamic prune of FP-tree[J].Journal of Shandong University of Technology,2011,41(4):49-55. |
| |
| Authors: | SONG Wei LIU Wen-bo LI Jin-hong |
| |
| Affiliation: | College of Information Engineering, North China University of Technology, Beijing 100144, China |
| |
| Abstract: | To solve the problem of huge memory usage of FP-tree construction and traversal in FP-growth,the dynamic-prune algorithm,a concurrent frequent itemsets mining algorithm based on the dynamic pruning FP-tree,was proposed.First,by recording the support counts of frequent items during the process of the FP-tree construction,the dynamic pruning algorithm of the FP-tree was implemented.Second,the construction of FP-tree and the discovery of frequent itemsets could be simultaneously realized by using the concurren... |
| |
| Keywords: | data mining FP-Tree frequent itemset dynamic prune concurrency |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《山东大学学报(工学版)》浏览原始摘要信息 |
|
点击此处可从《山东大学学报(工学版)》下载全文 |
|
